Output Moderation on WildGuard (test)
79.5F1 ScoreQwen3Guard-4B-Gen-strict
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3Guard-4B-Gen-strictStreaming=no, Moderation Policy=Gen-strict, Backbone Scale=4B2026.04 | 79.5 | |
| Qwen3Guard-8B-Gen-strictStreaming=no, Moderation Policy=Gen-strict, Backbone Scale=8B2026.04 | 78.9 | |
| Llama3-StreamGuard-3BStreaming=yes, Backbone Scale=3B2026.04 | 77.8 | |
| Llama3-StreamGuard-8BStreaming=yes, Backbone Scale=8B2026.04 | 77.8 | |
| Qwen3Guard-Stream-4B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=4B2026.04 | 77.4 | |
| Llama3-StreamGuard-1BStreaming=yes, Backbone Scale=1B2026.04 | 77.2 | |
| Qwen3Guard-Stream-8B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=8B2026.04 | 77 | |
| Qwen3Guard-Stream-8B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=8B2026.04 | 76.8 | |
| Qwen3Guard-Stream-4B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=4B2026.04 | 76.4 | |
| Qwen3Guard-Stream-0.6B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=0.6B2026.04 | 76.3 | |
| Qwen3Guard-Stream-0.6B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=0.6B2026.04 | 75.8 |